# HG changeset patch
# User casties
# Date 1366203261 -7200
# Node ID 88009fd07d31bc6543785dbcc69118b3b36eb4f2
VLP specific additions to ECHO_content product. First checkin.
diff -r 000000000000 -r 88009fd07d31 VLPExtension.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/VLPExtension.py Wed Apr 17 14:54:21 2013 +0200
@@ -0,0 +1,1329 @@
+"""
+This module contains extensions which where originally made for the VLP.
+"""
+from OFS.Cache import Cacheable
+from Products.PageTemplates.PageTemplateFile import PageTemplateFile
+from Products.PageTemplates.PageTemplate import PageTemplate
+from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
+from OFS.Image import File
+import xml.dom.minidom
+import urllib
+import xmlrpclib
+import vlp_xmlhelpers
+import sys
+import os
+from stat import *
+from types import *
+from Globals import package_home
+import transaction
+import Acquisition
+import re
+import logging
+
+from Products.ECHO_content.ECHO_collection import *
+from vlp_xmlhelpers import *
+try:
+ from Products.zogiLib import zogiLib
+except:
+ print "Zogilib not installed, VLP_resource will not work"
+
+
+def lemmatize(str):
+ """takes a str and addes links the dictionary service"""
+ server = xmlrpclib.ServerProxy("http://archimedes.fas.harvard.edu/cgi-bin/donatus-rpc")
+ if server:
+ splitted=str.split(" ")
+ wordlist=["%s"%split for split in splitted].join()
+ return wordlist
+
+
+
+
+def makeXML(str):
+
+ try:
+ dom=xml.dom.minidom.parseString(str)
+ return str
+ except:
+ str=str.replace("& ","& ")
+ return """
+ %s
+ """%str
+
+
+def checkXMLfrag(str):
+ """checks and returns str as XML fragment"""
+
+ xmltempl = """
+ %s"""
+
+ try:
+ dom=xml.dom.minidom.parseString(xmltempl%utf8ify(str))
+ return str
+ except:
+ str=str.replace("& ","& ")
+
+ dom=xml.dom.minidom.parseString(xmltempl%utf8ify(str))
+ return str
+
+
+
+def getText(nodelist):
+
+ rc = ""
+ for node in nodelist:
+ if node.nodeType == node.TEXT_NODE:
+ rc = rc + node.data
+ return rc
+
+class sendMailForm(ZopePageTemplate):
+ """sendMailForm"""
+ meta_type="sendMailForm"
+
+ _default_content_fn = os.path.join(package_home(globals()), 'zpt','sendMail_template.zpt')
+
+ manage_options = ZopePageTemplate.manage_options+(
+ {'label':'Main Config','action':'main_configForm'},
+ )
+
+ main_configForm = PageTemplateFile(
+ 'zpt/changeSendMailForm', globals())
+
+ def main_config(self, toAddrs,mailServer, subjectAdd=None, RESPONSE=None):
+ """main_config"""
+ self.toAddrs=toAddrs.split("\n")
+ self.mailServer=mailServer
+ self.subjectAdd=subjectAdd
+ if RESPONSE:
+ RESPONSE.redirect('manage_main')
+
+ def sendForm(self,fromaddr,subject,content,nextPage="index_html",RESPONSE=None):
+ """sendform"""
+ fromaddr=fromaddr.strip("\r\n\t") # sicherstellen dass keine zusaetzlichen headerzeilen eingefuegt werden
+ subject=subject.strip("\r\n\t") # sicherstellen dass keine zusaetzlichen headerzeilen eingefuegt werden
+ toaddrs=self.toAddrs
+
+ subject="%s %s"%(self.subjectAdd,subject)
+
+ msg = ("From: %s\r\nSubject: %s\r\nTo: %s\r\n\r\n"
+ % (fromaddr, subject, ", ".join(toaddrs)))
+ server = smtplib.SMTP(self.mailServer)
+ #server.set_debuglevel(1)
+ msg=msg+content
+ server.sendmail(fromaddr, toaddrs, msg)
+ server.quit()
+
+ if RESPONSE:
+ RESPONSE.redirect(nextPage)
+
+manage_addSendMailFormForm = PageTemplateFile(
+ 'zpt/addSendMailForm', globals(), __name__='manage_addSendMailFormFrom')
+
+from urllib import quote
+
+def manage_addSendMailForm(self, id, toAddrs,mailServer, title=None, text=None, subjectAdd=None,
+ REQUEST=None, submit=None):
+ "Add a Page Template with optional file content."
+ toAddrsList=toAddrs.split("\n")
+ id = str(id)
+ if REQUEST is None:
+ self._setObject(id, sendMailForm(id, text))
+ ob = getattr(self, id)
+ if title:
+ ob.pt_setTitle(title)
+ setattr(ob,'toAddrs',toAddrsList)
+ setattr(ob,'mailServer',mailServer)
+ setattr(ob,'subjectAdd',subjectAdd)
+ return ob
+ else:
+ file = REQUEST.form.get('file')
+ headers = getattr(file, 'headers', None)
+ if headers is None or not file.filename:
+ zpt = sendMailForm(id)
+ else:
+ zpt = sendMailForm(id, file, headers.get('content_type'))
+
+ self._setObject(id, zpt)
+
+ try:
+ u = self.DestinationURL()
+ except AttributeError:
+ u = REQUEST['URL1']
+
+ if submit == " Add and Edit ":
+ u = "%s/%s" % (u, quote(id))
+
+ ob = getattr(self, id)
+ if title:
+ ob.pt_setTitle(title)
+
+ setattr(ob,'toAddrs',toAddrsList)
+ setattr(ob,'mailServer',mailServer)
+ setattr(ob,'subjectAdd',subjectAdd)
+ REQUEST.RESPONSE.redirect(u+'/manage_main')
+ return ''
+
+
+class VLP_collectionFolder(Folder):
+ """klasse fuer folder innerhalb der collection"""
+ meta_type="VLP_collectionFolder"
+
+class VLP_essay(Folder):
+ """classe fr VLP essays"""
+
+ meta_type="VLP_essay"
+
+ manage_options = Folder.manage_options+(
+ {'label':'Main Config','action':'ConfigVLP_essayForm'},
+ {'label':'Generate Essay Template','action':'generateEssayTemplateHTML'},
+ )
+
+ def content_html(self,type='collection'):
+ """template fuer content"""
+ #templates = self.ZopeFind(self.aq_parent,obj_ids=[type+"_template"])
+ #
+ #if templates:
+ # return templates[0][1]()
+
+ if hasattr(self,type+"_template"):
+ obj=getattr(self,type+"_template")
+ return obj()
+ else:
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','ECHO_%s_template_standard.zpt'%type)).__of__(self)
+ pt.content_type="text/html"
+ return pt()
+
+ def ConfigVLP_essayForm(self):
+ """Form for adding"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','ChangeVLP_essay.zpt')).__of__(self)
+ return pt()
+
+ def ChangeVLP_essay(self,title,label,description,RESPONSE=None):
+ """Change vlp_essay"""
+ self.title=title
+ self.label=label
+ self.description=description
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+ def __init__(self,id,title,label):
+ """init"""
+ self.id=id
+ self.title=title
+ self.label=label
+
+ def index_html(self):
+
+ """show the rendered file"""
+
+ if hasattr(self,'essayTemplate.html'):
+ return getattr(self,'essayTemplate.html')()
+
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','essay_template.zpt')).__of__(self)
+ pt.content_type="text/html"
+ return pt()
+
+ def generateEssayTemplateHTML(self,RESPONSE=None):
+ """lege standard index.html an"""
+
+ if not hasattr(self,'essayTemplate.html'):
+ zt=ZopePageTemplate('essayTemplate.html')
+ self._setObject('essayTemplate.html',zt)
+ default_content_fn = os.path.join(package_home(globals()),
+ 'zpt/essay_template.zpt')
+ text = open(default_content_fn).read()
+ zt.pt_edit(text, 'text/html')
+
+ else:
+ return "already exists!"
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+ def getPageList(self):
+ """returns sorted list of (id,object) of page objects"""
+
+ def sortFind(x,y):
+ return cmp(x[0],y[0])
+
+# pages=[]
+# pagestmp=self.ZopeFind(self,obj_metatypes=['DTML Document','File'])
+# for page in pagestmp:
+# if not (page[1].getId()[0]=="."):
+# pages.append(page)
+
+ pages = self.objectItems(['DTML Document','File'])
+ pages.sort(sortFind)
+ #logging.debug("pageList=%s"%repr(pages))
+ return pages
+
+
+ def getPageXMLfrag(self, pageNum=None, pageId=None, pageObj=None):
+ """returns XML fragment of page with id"""
+ xml = None
+
+ if pageNum is not None:
+ pl = self.getPageList()
+ pageObj = pl[int(pageNum)-1][1]
+
+ if pageId is not None:
+ pageObj = getattr(self, pageId, None)
+
+ if pageObj is not None:
+ txt = ""
+ if pageObj.meta_type == 'File':
+ data = pageObj.data
+ #logging.debug("data=%s txt=%s"%(repr(data),txt))
+ while data is not None:
+ if isinstance(data, str):
+ txt += data
+ data = None
+ else:
+ txt += data.data
+ data = data.next
+
+ else:
+ # not a File object... perhaps its executable
+ txt += pageObj()
+
+ xml = checkXMLfrag(txt)
+
+ return unicodify(xml)
+
+ # TODO: Fix this
+ xml2html = xml2html
+ # TODO: especially this
+ link2html = link2html
+ checkRef = checkRef
+
+ def getPage(self,pagenum):
+ """gibt essay page mit num aus"""
+ def sortFind(x,y):
+ return cmp(x[0],y[0])
+ pages=[]
+ pagestmp=self.ZopeFind(self,obj_metatypes=['DTML Document','File'])
+ for page in pagestmp:
+ if not (page[1].getId()[0]=="."):
+ pages.append(page)
+
+ pages.sort(sortFind)
+ #print str(pages[int(pagenum)][1]())
+
+ if pages[int(pagenum)-1][1].meta_type=='File':
+ #return makeXML(str(pages[int(pagenum)-1][1]))
+ #txt=pages[int(pagenum)-1][1].data.decode('utf-8')
+ txt=pages[int(pagenum)-1][1].data
+ #print txt.encode('utf-8')
+ tmp =makeXML(txt)
+ logging.debug(txt)
+ return self.xml2html(tmp,quote="no")
+ else:
+ return self.xml2html(makeXML(pages[int(pagenum)-1][1]()),quote="no")
+
+ def nextPage(self,pagenum,url):
+ pages=len(self.ZopeFind(self,obj_metatypes=['DTML Document','File'])) # teste ob performance ok, sonst in variable
+ if int(pagenum)+1 <= pages:
+ retstr=url+"?p="+str(int(pagenum)+1)
+ return """| next | """%retstr
+
+ def previousPage(self,pagenum,url):
+
+ if int(pagenum)-1 > 0:
+ retstr=url+"?p="+str(int(pagenum)-1)
+ return """previous | """%retstr
+
+ def nextURL(self,pagenum,url):
+ pages=len(self.ZopeFind(self,obj_metatypes=['DTML Document','File'])) # teste ob performance ok, sonst in variable
+ if int(pagenum)+1 <= pages:
+ retstr=url+"?p="+str(int(pagenum)+1)
+ return retstr
+
+ def lastURL(self,pagenum,url):
+ # teste ob performance ok, sonst in variable
+ pages=len(self.ZopeFind(self,obj_metatypes=['DTML Document','File']))
+
+ return url+"?p="+str(pages)
+
+ def previousURL(self,pagenum,url):
+
+ if int(pagenum)-1 > 0:
+ retstr=url+"?p="+str(int(pagenum)-1)
+ return retstr
+
+
+def manage_addVLP_essayForm(self):
+ """Form for adding"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','AddVLP_essay.zpt')).__of__(self)
+ return pt()
+
+def manage_addVLP_essay(self, id,title,label,RESPONSE=None):
+ """add the copyright"""
+
+
+ self._setObject(id, VLP_essay(id, title,label))
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+
+class VLP_encyclopaedia(VLP_essay):
+ """essay"""
+
+ meta_type="VLP_encyclopaedia"
+
+ manage_options = VLP_essay.manage_options+(
+ {'label':'Load File','action':'loadNewFileForm'},
+ )
+
+
+ def loadNewFileForm(self):
+ """Neues XML-File einlesen"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','VLP_newfile.zpt')).__of__(self)
+ return pt()
+
+ def loadNewFile(self,RESPONSE=None):
+ """einlesen des neuen files"""
+ fileupload=self.REQUEST['fileupload']
+ if fileupload:
+ file_name=fileupload.filename
+ filedata=fileupload.read()
+
+ argv=vlp_xmlhelpers.proj2hash(self,filedata)
+ textsStr=string.join(argv['text']).encode('utf-8')
+
+ texts=textsStr.split("")
+
+ i=0
+ for text in texts:
+ i+=1
+ pageName='page%03d.xml'%i
+ pages=self.ZopeFind(self,obj_ids=[pageName])
+ if pages:
+ pages[0][1].update_data(text)
+
+ else:
+ zt=File(pageName,pageName,text,content_type="text/plain")
+ self._setObject(pageName,zt)
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+
+def manage_addVLP_encycForm(self):
+ """Form for adding"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','AddVLP_encyc.zpt')).__of__(self)
+ return pt()
+
+def manage_addVLP_encyc(self, id,title,label,RESPONSE=None):
+ """add the copyright"""
+
+
+ self._setObject(id, VLP_encyclopaedia(id, title,label))
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+class VLP_subcollection(ECHO_collection):
+ """ subcollection of elements"""
+
+ meta_type="VLP_subcollection"
+
+ def getVLPSubcollectionToc(self,type):
+
+ #different ordering depending on the type
+ if(type == "(Collection)"):
+ sort= "shortreference"
+ else:
+ sort = "startpages"
+
+ #content of journals also displayed if not online
+
+ if (type == "(JournalVolume)"):
+ online =""
+ else:
+ online ="AND online = 1"
+ sort=self.collectionSort(type)
+
+ item = [x for x in self.ZSQLSimpleSearch("""SELECT * FROM vl_literature
+ WHERE volumeid ~ '%s\\\\M' """%self.getId()
+ + """ %s AND not referenceType='%s' """%(online,type)
+ + """ORDER BY """ + sort)]
+
+ tocItem = [x for x in self.ZSQLSimpleSearch("""SELECT * FROM vl_literature
+ WHERE reference = '%s' """%self.getId()
+ + """AND online = 1 AND referenceType='%s' """%type
+ + """ORDER BY """ + sort)]
+
+
+
+ return tocItem+item
+
+ def checkForFrontMatter(self,item):
+ """Teste ob Frontmatter exists"""
+ if not item==self.getId():
+ return False
+
+ if self.ZopeFind(self,obj_ids=[self.getId()]):
+ return True
+ else:
+ return False
+
+ def generateSubCollectionFromDB(self):
+ """erzeuge subcollection"""
+ for item in self.ZSQLSimpleSearch("select * from vl_literature where volumeid like '%s'"%self.id):
+ manage_addECHO_link(self,item.reference,item.titlerefdisplay,item.titlerefdisplay)
+
+
+ def index_html(self):
+ """erzeuge darstellung"""
+
+ if hasattr(self,'subCollection_template.html'):
+ return getattr(self,'subCollection_template.html')()
+
+ pt=zptFile(self, 'zpt/subCollection_template.zpt')
+ return pt()
+
+
+def manage_addVLP_subCollection(self,id,title,label,RESPONSE=None):
+
+ self._setObject(id,VLP_subcollection(id,title,label))
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+from zope.publisher.interfaces import IPublishTraverse
+from zope.interface import implements
+from zope.publisher.interfaces import NotFound
+#from zope.app import zapi
+from zope.component import queryMultiAdapter
+try:
+ from ZPublisher.BaseRequest import DefaultPublishTraverse
+except:
+ pass
+
+class VLP_collection(ECHO_collection,Acquisition.Explicit):
+ """VLP spezifische Erweiterung der Collection"""
+
+
+
+ implements(IPublishTraverse)
+
+
+ def foxridgePath2vlp(self,url,mk,RESPONSE=None):
+ """convertiert einen pfad zu einer url in vlp"""
+ litRe = re.match(r".*lit([0-9]*)",url)
+ logging.debug("foxridgePath2vlp URL:"+repr(url))
+ lit = "lit"+litRe.group(1)
+ splitted=url.split("/")
+ path=splitted[-1].split(".")[0]
+ newUrl=lit+"?p=%s&mk=%s"%(path,mk)
+
+ if RESPONSE:
+ RESPONSE.redirect(newUrl)
+ return
+
+ return newUrl
+
+ def findObjFromLitName(self,fileName):
+ if not fileName[0:3]=="lit":
+ logging.error("getOrCreateFolder wrong filename: %s"%fileName)
+ return None
+
+
+ restName="%08d"%int(fileName[3:])
+
+ fs=(restName[0:2],restName[0:4],restName[0:6])
+
+ current =self
+ for f in fs:
+ obj = getattr(current,f,None)
+ if not obj: #subfolder existiert nicht
+ return None
+ current=obj
+
+ return getattr(current,fileName,None)
+
+ def publishTraverse(self,request,name):
+ """change the traversal if literature object"""
+
+ actual_url=request['ACTUAL_URL']
+ lastActual=actual_url.split("/")[-1]
+ logging.debug("pub_trav:"+actual_url)
+
+ if name.startswith("lit"): #umleitung wenn lit aufgerufen wirk
+ # umleitung auf den eigentlichen folder nur wenn direkt der Folder litXXX oder dessen index_html methode aufgerufen wird
+ if lastActual.startswith("lit") or (lastActual=="index_html") or (lastActual=="index_meta") or (lastActual=="getTitle") or (lastActual=="getMetaDataLink") or (lastActual=="hasTranscription") or (lastActual=="transcription"):
+ #obj=self. ZopeFind(self,obj_ids=[name],search_sub=1)
+ ob=self.findObjFromLitName(name)
+ if not ob:
+ return "LIt not found"
+ else:
+
+ logging.debug("request:"+repr(ob))
+ request.response.setStatus(200)
+ #if (lastActual=="index_meta"):
+ # logging.debug("index_meta requested")
+ # return ob.index_meta
+ return ob
+
+ else: ## andern falls transversiere zum parent.
+ obj = self.aq_parent
+ return obj
+ else: # mache gar nichts falls nicht lit aufgerufen wird
+
+
+ tr=DefaultPublishTraverse(self, request)
+ ob= tr.publishTraverse(request, name)
+
+ return ob
+ #raise NotFound(self.context, name, request)
+ #return repr(request)
+
+ meta_type="VLP_collection"
+ manage_options=ECHO_collection.manage_options+(
+ {'label':'Change Path','action':'VLP_path_configForm'},
+ {'label':'Update Library','action':'updateCollection'},
+ {'label':'Update Metadata','action':'updateCollectionMD'},
+ )
+ def getAllRessources(self):
+ """getallressources"""
+ res=self.ZopeFind(self,obj_metatypes=['VLP_resource'],search_sub=1)
+ ret=[]
+ for r in res:
+ ret.append([r[0],r[1].absolute_url()])
+
+ return ret
+
+ def generateSubCollections(self,errorsTXT="",forceUpdate=False,RESPONSE=None):
+ """erzeuge subcollectionen"""
+ logging.debug("generateSubCollections")
+ founds=self.ZSQLSimpleSearch("select * from vl_literature where referencetype in ('(Edited Book)','(Book)','(Collection)','(JournalVolume)','(Generic Container)')")
+
+ if RESPONSE is not None:
+ RESPONSE.setHeader('Content-Type','text/html')
+ self.REQUEST.RESPONSE.write("Create Subcollections
\n")
+ for found in founds:
+ try:
+ litid = str(found.reference)
+ foundCol=self.findObjFromLitName(litid)
+ #foundCol=self.ZopeFind(self,obj_ids=[litid])
+ if foundCol:
+ col = foundCol
+ logging.debug("generateSubCollections: subcollection %s exists (%s)"%(repr(col),found.reference))
+ logging.debug(repr([col.title,found.titlerefdisplay,col.label,found.titlerefdisplay]))
+ if (unicodify(col.title) != unicodify(found.titlerefdisplay)) or (unicodify(col.label) != unicodify(found.titlerefdisplay)):
+ # subcollection seems to have changed
+ logging.debug("generateSubCollections: subcollection has changed, recreating!")
+ col.aq_parent.manage_delObjects([col.getId()])
+ manage_addVLP_subCollection(self.getOrCreateFolderForFile(litid),litid,found.titlerefdisplay,found.titlerefdisplay)
+ else:
+ logging.debug("generateSubCollections: creating new subcollection %s"%found.reference)
+ manage_addVLP_subCollection(self.getOrCreateFolderForFile(litid),litid,found.titlerefdisplay,found.titlerefdisplay)
+
+ #teste ob es Images auf dem Server gibt mit gleichem Namen (frontmatter)
+ if os.path.exists(os.path.join(self.vlp_basis,litid)):
+ logging.debug("generateSubCollections: found frontmatter in %s"%litid)
+ obj=self.findObjFromLitName(litid)
+ if not self.ZopeFind(obj,obj_ids=[litid]):
+ metalink=self.REQUEST['URL1']+"/"+litid+"/"+litid+"/index_meta"
+ newObj=VLP_resource(litid,'',metalink,litid,litid,litid,'generated','book','','','','','','')
+ obj._setObject(litid,newObj)
+
+ genObj=getattr(obj,litid)
+ genObj.createIndexFile(forceUpdate=forceUpdate)
+
+ if RESPONSE is not None:
+ self.REQUEST.RESPONSE.write("%s
\n"%litid)
+ logging.debug("%s
\n"%litid)
+
+ except:
+ error=sys.exc_info()[0:2]
+ logging.error("generateSubCollections: ERROR in %s"%litid)
+ if RESPONSE is not None:
+ RESPONSE.write("(ERROR updateII(%s): %s %s TXT: %s)\n
"%(litid,error[0],error[1],sys.exc_info()[2]))
+ RESPONSE.write("(ERROR (%s): %s %s)
\n"%(litid,error[0],error[1]))
+ logging.error("generateSubCollections: %s %s"%error)
+ self.REQUEST.RESPONSE.write("(ERROR (%s): %s %s)\n"%(litid,repr(error[0]),repr(error[1])))
+ errorsTXT+="ERROR: No subcollection of %s (ERROR: %s %s)
\n"%(litid,error[0],error[1])
+ errorsTXT+="No subcollection of %s "%litid+"(ERROR: %s %s)
"%error
+
+ return errorsTXT
+
+ def VLP_path_configForm(self):
+ """change pt"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','ChangeVLPPath.zpt')).__of__(self)
+ return pt()
+
+ def VLP_path_config(self,path,RESPONSE=None):
+ """config"""
+ self.vlp_basis=path
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+
+ def getOrCreateFolderForFile(self,fileName):
+
+ if not fileName[0:3]=="lit":
+ logging.error("getOrCreateFolder wrong filename: %s"%fileName)
+ return None
+
+ try:
+ restName="%08d"%int(fileName[3:])
+ except:
+ logging.error("getOrCreateFolder wrong filename: %s"%fileName)
+ return None
+
+ fs=(restName[0:2],restName[0:4],restName[0:6])
+
+ current =self
+ for f in fs:
+ obj = getattr(current,f,None)
+ if not obj:
+ newObj=VLP_collectionFolder(f)
+ current._setObject(f,newObj)
+ obj = getattr(current,f)
+ current=obj
+
+ return current
+
+ def changeOrAddResources(self,forceUpdate=False,RESPONSE=None):
+ """changes ord updates all resources found in the file system"""
+
+ errorsTXT="Errors
"
+ if RESPONSE is not None:
+ RESPONSE.setHeader('Content-Type','text/html')
+ RESPONSE.write("")
+
+ files=os.listdir(self.vlp_basis)
+ i=0
+ for fileName in files:
+ if i<100:
+ i+=1
+ else:
+ i=0
+ j=0
+ while j<5:
+ try:
+ transaction.get().commit()
+ j=6
+ except:
+ logging.error("Commit: %s"%j)
+ j+=1
+
+ RESPONSE.write("committed
")
+ if fileName[0:3]=="lit":
+ metalink=self.REQUEST['URL1']+"/"+fileName+"/index_meta"
+
+ folder=self.getOrCreateFolderForFile(fileName) #get the folder where fileName lives or should live
+ if not folder: #folder gave an error
+ continue
+ try:
+ if not hasattr(folder,fileName):
+ # create new resource
+ logging.debug("updateCollection: new %s"%fileName)
+ if RESPONSE is not None:
+ RESPONSE.write("new: %s
\n"%fileName)
+ logging.debug("new: %s \n"%fileName)
+ newObj=VLP_resource(fileName,'',metalink,fileName,fileName,fileName,'generated','book','','','','','','')
+
+ folder._setObject(fileName,newObj)
+
+ if RESPONSE is not None:
+ RESPONSE.write("got: %s "%fileName)
+
+ genObj=getattr(folder,fileName)
+ logging.debug("got: %s "%fileName)
+
+ logging.debug("updateCollection: inspecting %s"%fileName)
+ # create index
+ if hasattr(genObj,'createIndexFile'):
+ try:
+ logging.debug("updateCollection: creating index for %s"%fileName)
+ msg = genObj.createIndexFile(forceUpdate=forceUpdate)
+ if msg and RESPONSE is not None:
+ RESPONSE.write(msg)
+ except:
+ error=sys.exc_info()[0:2]
+ if RESPONSE is not None:
+ RESPONSE.write("(ERROR Update(%s): %s %s %s) "%(fileName,error[0],error[1],sys.exc_info()[2]))
+ errorsTXT+="
ERROR creating index for %s "%fileName+"(ERROR: %s %s)
\n"%error
+
+ # update pageSizeSum for subcollections
+ if genObj.meta_type=="VLP_subcollection":
+ if RESPONSE is not None:
+ RESPONSE.write(" is subcollection")
+ logging.debug("updateCollection: %s is subcollection"%fileName)
+ genObj.pageSizeSum=getattr(genObj,fileName).getPageSizeSum()
+ else:
+ genObj.pageSizeSum=genObj.getPageSizeSum()
+
+ if RESPONSE is not None:
+ RESPONSE.write("\n")
+
+ except:
+ error=sys.exc_info()[0:2]
+ logging.error("updateCollection: ERROR in %s (%s %s)"%(fileName,error[0],error[1]))
+ if RESPONSE is not None:
+ RESPONSE.write("(ERROR updateII(%s): %s %s %s) "%(fileName,error[0],error[1],sys.exc_info()[2]))
+ errorsTXT+="File not created:%s (ERROR: %s %s)
\n"%(fileName,error[0],error[1])
+ return errorsTXT
+
+ def updateCollection(self,forceUpdate=True,RESPONSE=None):
+ """liest verzeichnisse aus dem pfad und legt sie dann als objekte in den ordner"""
+
+ # update subcollections
+ errorsTXT=""
+ errorsTXT+=self.changeOrAddResources(forceUpdate, RESPONSE);
+ errorsTXT+=self.generateSubCollections(forceUpdate=forceUpdate,RESPONSE=RESPONSE)
+ errorsTXT+="\n"
+ if RESPONSE is not None:
+ RESPONSE.write(errorsTXT)
+ RESPONSE.write("")
+
+ def updateCollectionMD(self,RESPONSE=None):
+ """updateMD"""
+ files=os.listdir(self.vlp_basis)
+ for fileName in files:
+ if fileName[0:3]=="lit":
+ genObj=getattr(self,fileName)
+ genObj.copyIndex_meta2echo_resource()
+ genObj.generate_title()
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+ def copyFullTextsFromDB(self,RESPONSE=None):
+ """copy fulltext aus DB"""
+
+ ress=self.ZopeFind(self,obj_metatypes=['VLP_resource'])
+ ret=""
+ for res in ress:
+ tmp=res[1].copyTranscriptionFromDB()
+ ret+=tmp
+
+ if RESPONSE:
+ RESPONSE.write(tmp+"\n")
+ if not RESPONSE:
+ return ret
+ else:
+ RESPONSE.write("END\n")
+
+
+def manage_addVLP_collectionForm(self):
+ """Form for adding a ressource"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','AddVLP_collectionForm.zpt')).__of__(self)
+ return pt()
+
+
+
+def manage_addVLP_collection(self,id,title,label,description,contentType,responsible,weight,sortfield,path,coords="",secondaryLinkTitle="",secondaryLink="",credits=None,RESPONSE=None,imageTag="",bgcolour=""):
+ """add a echo collection"""
+
+
+ newObj=VLP_collection(id,title,label,description,contentType,responsible,credits,weight,sortfield,coords,secondaryLinkTitle=secondaryLinkTitle,secondaryLink=secondaryLink,imageTag=imageTag,bgcolour="")
+
+ self._setObject(id,newObj)
+ setattr(newObj,'path',path)
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+
+
+class VLP_resource(ECHO_resource,Cacheable):
+ """VLP spezifische Erweiterung"""
+
+ meta_type="VLP_resource"
+
+ def _p_resolveConflict(self,oldstate,savedstate,newstate):
+ logging.debug("updateCollection: Have to resolve conflict!")
+ return newstate
+
+ #vlp_basis="/mpiwg/online/permanent/vlp"
+
+
+
+ referencetypes=[]
+
+ manage_options=ECHO_resource.manage_options+Cacheable.manage_options+(
+ {'label':'Update Index','action':'createIndexFile'},
+ {'label':'Reset MetaLink','action':'resetMetaLink'},
+ {'label':'Generate Title','action':'generate_title'},
+ {'label':'Generate Library Template','action':'generateLibraryTemplateHTML'},
+ )
+
+ def getMetaDataLink(self):
+ """link auf die metatdaten"""
+ return self.absolute_url()+"/index_meta"
+
+
+ def getTitle(self):
+ """Title der Ressource"""
+ title= self.ZSQLSimpleSearch("""select title from vl_literature where reference= \'%s\' """ %self.getId())[0].title
+ logging.debug(title)
+ return title
+
+
+
+ def getImagePath(self):
+ """Pfad zu den Images"""
+ path=None
+
+ if os.path.isdir(os.path.join(self.vlp_basis,self.resourceID,'pageimg')):
+ path= os.path.join(self.vlp_basis,self.resourceID,'pageimg')
+ elif os.path.isdir(os.path.join(self.vlp_basis,self.resourceID,'pages')):
+ path = os.path.join(self.vlp_basis,self.resourceID,'pages')
+ # workaround in some cases there seem to be no pictures in pages
+
+ if os.path.isdir(os.path.join(self.vlp_basis,self.resourceID,'pagesHi')):
+
+
+ pagesHi = os.listdir(os.path.join(self.vlp_basis,self.resourceID,'pagesHi'))
+ if path is None:
+ return os.path.join(self.vlp_basis,self.resourceID,'pagesHi')
+
+ pages = os.listdir(path)
+
+ if len (pagesHi) > len(pages):
+
+ countHi=0
+ for p in pagesHi:
+ dat,ext = os.path.splitext(p)
+ if ext.lower() in [".tiff",".tif",".jpg"]:
+ countHi+=1
+ count=0
+ for p in pages:
+ dat,ext = os.path.splitext(p)
+ if ext.lower() in [".tiff",".tif",".jpg"]:
+ count+=1
+
+ if countHi > count:
+ path=os.path.join(self.vlp_basis,self.resourceID,'pagesHi')
+
+ logging.error("pages < pagesHi: %s"%self.resourceID)
+ if path is None:
+
+
+ if len (os.listdir(os.path.join(self.vlp_basis,self.resourceID,'pagesHi'))) > len(os.listdir(path)):
+
+
+
+ path=os.path.join(self.vlp_basis,self.resourceID,'pagesHi')
+ logging.error("pages < pagesHi: %s"%self.resourceID)
+ else:
+
+ logging.error("no images: %s"%self.resourceID)
+ return None
+
+ return path
+
+
+ def transcription(self):
+ """show the rendered transcriptiofile"""
+
+ if hasattr(self,'libraryTranscriptionTemplate.html'):
+ return getattr(self,'libraryTranscriptionTemplate.html')()
+
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','library_transcriptionTemplate.zpt')).__of__(self)
+ pt.content_type="text/html"
+ return pt()
+
+
+
+ def identifyMediaType(self):
+ """identifiziert den Medientype aus der VLP Datenbank"""
+ founds=self.ZSQLSimpleSearch('select * from vl_literature where reference=\''+self.resourceID+'\' order by id')
+ if (not founds) or (len(founds)==0):
+ self.mediaType="generic" # steht nicht in der Datenbank, dann nimm generisch an
+ return self.mediaType
+
+
+ if founds[0].referencetype =="Audio":
+ self.mediaType ="audio"
+ elif founds[0].referencetype =="Film":
+ self.mediaType ="video"
+ else:
+ self.mediaType ="image" # nimm an, dass alle anderen Eintrage in der Datenbank auf images verweisen (Buecher oder Fotografien).
+
+ return self.mediaType
+
+ def getMediaType(self,cached=False):
+ """give the Media-type back, if chached False, then get it from the database"""
+
+ if (not hasattr(self,'mediaType')) or (self.mediaType=="") or (not cached):
+ self.identifyMediaType()
+
+ return self.mediaType
+
+
+
+
+ def copyTranscriptionFromDB(self):
+ """checks if transcription exits in DB"""
+ founds=self.ZSQLSimpleSearch('select * from vl_transcript where source=\''+self.resourceID+'\' order by id')
+
+
+ ret="""
+ """
+
+ if founds:
+
+ for found in founds:
+
+ text=found.transcript
+ if not text: text=""
+ ret+=""+text+""
+
+ ret+=""
+ re2=ret[0:]
+ re3=self.unicodify(re2)
+ #re3=re2
+ ft=self.ZopeFind(self,obj_metatypes=['ECHO_fullText'])
+
+ if ft:
+
+ ft[0][1].pt_edit(re3,'text/xml')
+
+ else:
+
+ self._setObject('fulltext',ECHO_fullText(id,''))
+
+ try:
+ getattr(self,'fulltext').pt_edit(re3.encode('utf-8','ignore'),'text/xml')
+ except:
+ getattr(self,'fulltext').pt_edit(re3.encode('latin-1').decode('utf-8'),'text/xml')
+
+ return "FT: %s"%self.getId()
+ else:
+ return "no: %s"%self.getId()
+
+ def hasTranscription(self):
+ """transcription"""
+
+ if not hasattr(self,'fulltext'):
+ self.copyTranscriptionFromDB()
+ if not hasattr(self,'fulltext'): #still not
+ return False
+
+ return True
+
+ def resetMetaLink(self,all="no",RESPONSE=None):
+ """resets metalink to standard resp. in case of server change it sets to the new server url"""
+ if all=="yes":
+ self.metalink=self.absolute_url()+"/index_meta"
+ else:
+ splitted=self.metalink.split("/")
+ if (len(splitted)>1) and (splitted[len(splitted)-1]=="index_meta") and (splitted[len(splitted)-2]==self.getId()): # heuristic nur generische Metadatafiles andern
+ self.metalink=self.absolute_url()+"/index_meta"
+
+ if RESPONSE:
+ return "done"
+
+ def show(self):
+ """show the rendered file"""
+
+ mt = self.getMediaType()
+
+ if (mt in ['video','audio']):
+ pt = self.getVLPTemplate('libraryMovieTemplate')
+ else: #zur zeit werden alle anderen type auf das libraryTemplate abgebildet.
+
+ if self.REQUEST.get('p',None): #make sure that parameter p exists
+ #self.REQUEST.set('pn',self.file2page(self.REQUEST.get('p',None)))
+ params = "pn=%s"%self.file2page(self.REQUEST.get('p',None))
+ mk = self.REQUEST.get('mk',None)
+ if mk:
+ params += "&mk=%s"%mk
+ self.REQUEST.RESPONSE.redirect(self.REQUEST['URL']+'?'+params)
+
+ pt = self.getVLPTemplate('libraryTemplate')
+
+ return pt()
+
+ def getVLPTemplate(self,name):
+ html=name+".html"
+ if hasattr(self,html):
+ return getattr(self,html)
+
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt',name+'.zpt')).__of__(self)
+ pt.content_type="text/html"
+ return pt
+
+ def index_html(self):
+ """index_html"""
+ #return self.REQUEST
+ if not self.REQUEST.has_key("ws"):
+ self.REQUEST.form["ws"]="1.5"
+
+ return self.show()
+
+ def generateLibraryTemplateHTML(self,RESPONSE=None):
+ """lege standard index.html an"""
+
+ if not hasattr(self,'libraryTemplate.html'):
+ zt=ZopePageTemplate('libraryTemplate.html')
+ self._setObject('libraryTemplate.html',zt)
+ default_content_fn = os.path.join(package_home(globals()),
+ 'zpt/library_template.zpt')
+ text = open(default_content_fn).read()
+ zt.pt_edit(text, 'text/html')
+
+ else:
+ return "already exists!"
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+
+ def index_meta(self,RESPONSE=None):
+ """index_meta"""
+
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','index_meta.zpt')).__of__(self)
+ pt.content_type="text/xml"
+ x= pt.pt_render()
+ #logging.debug("index_meta 4:"+x)
+ if RESPONSE:
+ RESPONSE.setHeader("Content-Type","text/xml")
+ return x
+ def file2page(self,p):
+ """converts filename to pagenumber"""
+
+ #dom=xml.dom.minidom.parse(ECHO_helpers.urlopen(getattr(self,'index.xml').absolute_url()))
+ index=getattr(self,'index.xml')
+
+ txt=index.pt_render()
+ dom=xml.dom.minidom.parseString(txt)
+
+ for page in dom.getElementsByTagName('page'):
+ # pageummer mit lo oder hi sind aequivalent
+ if (page.getAttribute('file')==p) or ("%slo"%page.getAttribute('file')==p) or ("%shi"%page.getAttribute('file')==p):
+ nr=page.getAttribute('nr')
+
+ return nr
+
+ return 0
+
+ def getPageSizeSum(self):
+ """generate average page size"""
+
+ #size of hi resolution
+ files=[]
+ try:
+ pathHi=os.path.join(self.vlp_basis,self.resourceID,'pages')
+ files=os.listdir(pathHi)
+ hi=0
+ for f in files:
+ hi+=os.stat(os.path.join(pathHi,f))[ST_SIZE]
+
+ except:
+ hi=0
+
+ #size of hi resolution
+ try:
+ pathHi=os.path.join(self.vlp_basis,self.resourceID,'pagesLo')
+ files=os.listdir(pathHi)
+ lo=0
+ for f in files:
+ lo+=os.stat(os.path.join(pathHi,f))[ST_SIZE]
+
+ except:
+ lo=0
+
+
+ return (hi,lo,len(files))
+
+
+ def getPageWeights(self):
+ """average Page sizes in kBytes"""
+
+ res=getattr(self,'pageSizeSum',(0,0,1))
+ return (res[0]/(1024*res[2]),res[1]/(1024*res[2]))
+
+
+
+ def dir2index(self):
+ """dir to index"""
+
+ excludeNames=['Icon']
+
+
+ def calculateName(str):
+ name=os.path.splitext(str[1:])[0]
+ ret="%s: %s"%(str[0],name)
+ return ret
+
+ self.imagePathFull=self.getImagePath();
+ self.imagePath=self.imagePathFull.split("/")[-1]
+ if (self.imagePath is None):
+ return None
+
+ temp=[]
+ ret = os.listdir(self.imagePathFull)
+
+ ret.sort()
+ for x in ret:
+ if (not (x[0] in ('.',':'))) and (not x[0:4] in excludeNames):
+ temp.append((calculateName(x),os.path.splitext(x)[0]))
+ return temp
+
+
+ def firstPage(self,url=None):
+ """showlink to the first image"""
+ if self.REQUEST.get('pn','1')=="1": #erste seinte dann kein a tag
+ return """
first"""
+
+ else:
+ ws=self.REQUEST.get('ws','1')
+ return """
+
first
+
+ """%(self.REQUEST['URL']+"?pn=1&ws=%s"%ws)
+
+ def lastPage(self,url=None):
+ """showlink to the first image"""
+ pages=self.readIndexFile(url)
+ if pages:
+ ln=len(pages)
+
+ if (self.REQUEST.get('pn')==str(ln)) or (ln==1): #letzte seite dann kein a tag oder nur eine Seite
+ return """
last"""
+
+ else:
+ ws=self.REQUEST.get('ws','1')
+ return """
+
last
+
+ """%(self.REQUEST['URL']+"?pn="+str(ln)+"&ws="+ws)
+
+ def prevPage(self,url=None):
+ """showlink to the first image"""
+
+
+ nn = int(self.REQUEST.get('pn','1'))-1
+ if nn < 1: #letzte seite dann kein a tag
+ return """
prev"""
+
+ else:
+ ws=self.REQUEST.get('ws','1')
+ return """
+
prev
+
+ """%(self.REQUEST['URL']+"?pn="+str(nn)+"&ws="+ws)
+
+ def nextPage(self,url=None):
+ """showlink to the first image"""
+ pages=self.readIndexFile(url)
+ if pages:
+ ln=len(pages)
+
+ nn = int(self.REQUEST.get('pn','1'))+1
+ if (nn>int(ln)) or (ln==1): #letzte seite dann kein a tag
+ return """
next"""
+
+ else:
+ ws=self.REQUEST.get('ws','1')
+ return """
+
next
+
+ """%(self.REQUEST['URL']+"?pn="+str(nn)+"&ws="+ws)
+
+
+ def readIndexFile(self,url=None):
+ """reads the indexfile. presently url not None isn't implemented. In the future url can be defined."""
+ if not url:
+ urlTmp=self.absolute_url()+"/index.xml"
+
+ if self.ZCacheable_isCachingEnabled():
+
+ result = self.ZCacheable_get(view_name=urlTmp)
+ if result is not None:
+ # Got a cached value.
+ return result
+
+ pagelist=[]
+
+ if not url:
+
+ xmlTxt=getattr(self,'index.xml')()
+ dom=xml.dom.minidom.parseString(xmlTxt)
+ else:
+ fh=ECHO_helpers.urlopen(urlTmp)
+ dom=xml.dom.minidom.parse(fh)
+
+
+ for page in dom.getElementsByTagName('page'):
+ text=getText(page.childNodes)
+ pageNum=page.getAttribute('nr')
+ fileName=page.getAttribute('file')
+ pagelist.append((pageNum,text,fileName))
+
+ self.ZCacheable_set(pagelist,view_name=urlTmp)
+ return pagelist
+
+ def getFileName(self):
+ """getNameOfCurrentFile"""
+ try:
+ pn=int(self.REQUEST.get('pn','1'))
+ except:
+ pn=1
+ pageinfo=self.readIndexFile()[pn-1]
+ return pageinfo[2]
+
+ def createIndexFile(self,forceUpdate=False,RESPONSE=None):
+ """create index file"""
+ logging.debug("createindexfile of %s"%self.id)
+
+ if hasattr(self,'index.xml'):
+ # index exists
+ zt=getattr(self,'index.xml')
+ if not forceUpdate:
+ # check if directory is newer (self.imagePath sould be set by now)
+ path = self.getImagePath()
+ if (path is None):
+ return "CREATE INDEX FILE NOT POSSIBLE"
+ imgdir = os.path.join(path)
+ dirtime = os.path.getmtime(imgdir)
+ zttime = zt.bobobase_modification_time()
+ logging.debug("createindexfile: dir %s of %s index of %s"%(imgdir,dirtime,zttime))
+ if dirtime < zttime:
+ # nothing to do
+ logging.debug("createindexfile: dir %s older than index"%(imgdir))
+ return "index is up to date"
+
+ else:
+ # create new index template
+ zt=ZopePageTemplate('index.xml')
+ self._setObject('index.xml',zt)
+
+ # fill index template
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','index_template.zpt')).__of__(self)()
+ #logging.debug("createindexfile uses %s"%pt)
+ zt.pt_edit(pt, 'text/xml')
+ transaction.get().commit()
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
+
+def manage_addVLP_resourceForm(self):
+ """Form for adding a ressource"""
+ pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','AddVLP_resourceForm.zpt')).__of__(self)
+ return pt()
+
+
+
+def manage_addVLP_resource(self,id,title,label,description,responsible,link,metalink,weight,resourceID=None,contentType=None,renderingType=None,credits=None,coords=None,RESPONSE=None):
+ """addaresource"""
+
+
+ if metalink=='':
+ metalink=self.absolute_url()+"/"+id+"/index_meta"
+
+ newObj=VLP_resource(id,link,metalink,resourceID,title,label,description,contentType,renderingType,responsible,credits,weight,coords)
+
+ self._setObject(id,newObj)
+
+ if RESPONSE is not None:
+ RESPONSE.redirect('manage_main')
+
diff -r 000000000000 -r 88009fd07d31 VLP_collection.gif
Binary file VLP_collection.gif has changed
diff -r 000000000000 -r 88009fd07d31 VLP_ressource.gif
Binary file VLP_ressource.gif has changed
diff -r 000000000000 -r 88009fd07d31 __init__.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/__init__.py Wed Apr 17 14:54:21 2013 +0200
@@ -0,0 +1,52 @@
+import VLPExtension
+
+
+
+def initialize(context):
+ """initialize OSAS"""
+
+
+
+ context.registerClass(
+ VLPExtension.VLP_resource,
+ constructors = (
+ VLPExtension.manage_addVLP_resourceForm,
+ VLPExtension.manage_addVLP_resource
+ ),
+ icon = 'VLP_ressource.gif'
+ )
+
+ context.registerClass(
+ VLPExtension.VLP_collection,
+ constructors = (
+ VLPExtension.manage_addVLP_collectionForm,
+ VLPExtension.manage_addVLP_collection
+ ),
+ icon = 'VLP_collection.gif'
+ )
+
+ context.registerClass(
+ VLPExtension.VLP_essay,
+ constructors = (
+ VLPExtension.manage_addVLP_essayForm,
+ VLPExtension.manage_addVLP_essay
+ )
+ )
+
+ context.registerClass(
+ VLPExtension.VLP_encyclopaedia,
+ constructors = (
+ VLPExtension.manage_addVLP_encycForm,
+ VLPExtension.manage_addVLP_encyc
+ )
+ )
+
+ context.registerClass(
+ VLPExtension.sendMailForm,
+ constructors = (
+ VLPExtension.manage_addSendMailFormForm,
+ VLPExtension.manage_addSendMailForm
+ )
+ )
+
+
\ No newline at end of file
diff -r 000000000000 -r 88009fd07d31 vlp_xmlhelpers.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/vlp_xmlhelpers.py Wed Apr 17 14:54:21 2013 +0200
@@ -0,0 +1,466 @@
+from sys import argv
+
+import string
+import logging
+import xml.dom.minidom
+#import Ft.Xml.XLink.Processor
+#import Ft.Xml.XLink.XLinkElements
+
+#from Ft.Xml import XPath
+#from Ft.Xml.XPath import Evaluate
+#from Ft.Xml.XLink import XLINK_NAMESPACE
+#from Ft.Xml.XLink import XLinkElements
+import cStringIO
+#from Ft.Xml.Domlette import NonvalidatingReader, PrettyPrint,Print
+#from Ft.Xml import EMPTY_NAMESPACE
+#from Ft.Lib import Uri
+import xml.etree.ElementTree as ET
+import urllib
+import re
+from Products.ECHO_content.ECHO_collection import unicodify,utf8ify
+
+patternTXT=r"<\s*txt.*?>(.*?)"
+regexpTXT = re.compile(patternTXT, re.IGNORECASE + re.DOTALL)
+patternPage=r"<\s*page.*?>(.*?)"
+regexpPage = re.compile(patternPage, re.IGNORECASE + re.DOTALL)
+
+#xml2htmlArray={'WEB_normal':('','
'),'Normal':('','
'),'WEB_picture':('','
'),'WEB_figuretitle':('','
'),'WEB_bibliography':('','
'),'Web_kursiv':('',''),'WEB_kursiv':('',''),'WEB_hyperlink':('',''),'Hyperlink':('',''),'Picture':('','
'),'FigureTitle':('','
')}
+#
+#def addToDict(dict,name,value):
+# if name=="":
+# return 0
+# else:
+#
+# if not dict.has_key(name):
+# dict[name]=[] # als array anlegen
+#
+# dict[name].append(value)
+# return 1
+#
+#def proj2hash(self,xmlstring):
+# """wandelt xml-files fuer die projekte in ein hash"""
+#
+# dom=xml.dom.minidom.parseString(xmlstring)
+#
+#
+# list={}
+#
+# #gettitle
+# pars=Evaluate('par',dom.getElementsByTagName('part')[0])
+# for par in pars:
+# className=par.getAttribute('class')
+# content=getText(self,par.childNodes)
+# addToDict(list,className,content)
+#
+#
+# sectionXPath="section"
+#
+#
+# sections=Evaluate(sectionXPath,dom.getElementsByTagName('part')[0])
+#
+# while sections:
+#
+# for section in sections:
+#
+# sec=parseSection(self,section)
+#
+# if sec[0]=="WEB_project_header": # Sonderfall project
+# addToDict(list,'WEB_project_header',sec[1]) # store title
+# addToDict(list,'WEB_project_description',sec[2]) #store description
+# else: # no information in heading
+# level=int(sec[3])+2
+# aTag=""%level
+# eTag=""%level
+# addToDict(list,"text",aTag+sec[1]+eTag)
+# addToDict(list,"text",sec[2])
+# sectionXPath+="/section"
+# sections=Evaluate(sectionXPath,dom.getElementsByTagName('part')[0])
+# return list
+#
+#
+#def parseSection(self,section):
+# type=""
+# header=""
+# level=section.getAttribute('level')
+# for heading in section.childNodes:
+# if getattr(heading,'tagName','')=="heading":
+#
+# type=heading.getAttribute('class')
+# header=getText(self,heading.childNodes)
+#
+# if type=="": # falls heading fehlt, pruefe ob erster par richtig
+# par=section.getElementsByTagName('par')[0]
+# type=par.getAttribute('class')
+# header=getText(par.childNodes)
+#
+# #print section.childNodes
+# #pars=Evaluate('par',section)
+# pars=section.childNodes
+# content=par2html(self,pars)
+# #print "CONTENT",repr(content)
+# return (type,header,content,level)
+#
+#def parseTable(table):
+# fields={}
+# rows=table.getElementsByTagName('html:tr')
+# for row in rows:
+# #print "ROW"
+# cols=row.getElementsByTagName('html:td')
+#
+# #Name des Datenfeldes einlesen
+# try:
+# field=cols[0].getElementsByTagName('par')[0].getAttribute('class')
+# #print "field",field
+# except:
+# print "error"
+# field=""
+#
+# #Wandeln der Eintrge in HTML
+#
+# #pars=cols[1].getElementsByTagName('par')
+# pars=cols[1].childNodes
+#
+# html=par2html(self,pars,tags=("",";"))
+#
+# addToDict(fields,field,html)
+# #print fields
+# return fields
+#
+#def par2html(self,pars,tags=None):
+# html=""
+#
+# for par in pars:
+# tagName=getattr(par,'tagName','')
+# if tagName in ["par","inline"]:
+# #print repr(par.getAttribute('class')),xml2htmlArray.get(par.getAttribute('class'),'NOT FOUND')
+# #print "par",par
+# if not tags:
+# try:
+# tag=xml2htmlArray[par.getAttribute('class')]
+# except:
+# tag=('','
')
+# else:
+# tag=tags
+# #print "TAG",tag
+# content=getText(self,par.childNodes,par.getAttribute('class'))
+#
+#
+#
+# #print par.getAttribute('class'),node
+# try:
+# html+=tag[0]+content+tag[1]
+# except:
+# html=+tag[0]+content+tag[1]
+#
+# elif tagName=="pb":
+# html+=""
+#
+#
+# try:
+#
+# return html
+# except:
+# return ""
+
+def getXlink(nodes):
+ """searches xlinks and gives them back as html"""
+ ret=""
+ for node in nodes:
+ if node.attributes:
+ if 'xlink:type' in node.attributes.keys(): #is a xlink?
+ ret +=xlink2html(node)
+ return ret
+
+def checkRef(self,ref):
+ """teste ob reference angezeigt werden sollen"""
+ dbs={'vl_literature':'AND online = \'1\'',
+ 'vl_technology':'AND complete =\'yes\'',
+ 'vl_people':'AND complete =\'yes\'',
+ 'vl_sites':'AND complete =\'yes\'',
+ 'vl_transcript':'AND complete =\'yes\'',
+ 'vl_essays':'AND online =\'yes\'',
+ 'vl_categories':''
+ }
+ res=None
+ for db in dbs.keys():
+ searchStr=str("select reference from %s where reference =\'%s\' %s"%(db,ref,dbs[db]))
+ res=res or self.search(var=searchStr)
+ return res
+
+def link2html(self,str):
+ """link2html links in html wandeln"""
+ if str:
+
+ str=re.sub("\&","&",str)
+ dom=xml.dom.minidom.parseString(""+utf8ify(str)+"")
+
+
+ links=dom.getElementsByTagName("link")
+
+
+ for link in links:
+ link.tagName="a"
+ ref=link.getAttribute("ref")
+ pn=link.getAttribute("page")
+ mk=link.getAttribute("mk")
+ href= link.getAttribute("href")
+ if href:
+ link.setAttribute("class","external")
+
+ if self.checkRef(ref):
+ more = ""
+ if pn:
+ more += "&page=%s"%pn
+
+ if mk:
+ more += "&mk=%s"%mk
+
+ link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref+more)
+
+
+ newxml=dom.toxml('utf-8')
+
+
+
+ retStr=regexpTXT.search(newxml)
+ retStr = retStr.group(1)
+
+ return retStr.decode('utf-8') # we return unicode
+
+ return u""
+
+def related2html(self,str):
+ """related library items: xlinks in html wandeln / mb 22.11.2006"""
+ if str:
+
+ str=re.sub("\&","&",str)
+ dom=xml.dom.minidom.parseString(""+utf8ify(str)+"")
+ links=dom.getElementsByTagName("link")
+
+ for link in links:
+ link.tagName = "a"
+ ref = link.getAttribute("ref")
+ pn = link.getAttribute("page")
+ obj = ref[0:3]
+
+ """erweiterung der related items von literatur auf weitere datenbankobjekte, mb 09.06.2009"""
+ searchStr = ''
+ if obj == 'lit':
+ searchStr="select fullreference, online from vl_literature where reference =\'%s\' and authorized = 1"%(ref)
+ elif obj == 'sit':
+ searchStr="select reference from vl_sites where reference =\'%s\' and complete = 'yes'"%(ref)
+ elif obj == 'per':
+ searchStr="select reference from vl_people where reference =\'%s\' and complete = 'yes'"%(ref)
+ elif obj == 'tec':
+ searchStr="select reference from vl_technology where reference =\'%s\' and complete = 'yes'"%(ref)
+ elif obj == 'exp':
+ searchStr="select reference from vl_experiments where reference =\'%s\' and complete = 'yes'"%(ref)
+
+ res = self.search(var=searchStr)
+
+ if res:
+ if obj == 'lit':
+ if res[0]['online'] == 1:
+ # literatur item online verfuegbar
+ if pn:
+ link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref+"&page="+pn)
+ else:
+ link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref)
+
+ link.setAttribute("title", "click to view!")
+ link.removeAttribute("ref")
+
+ # prefix preceding the link
+ prefix = dom.createTextNode(U"\u2013\u0020") # = ndash + space
+ dom.documentElement.insertBefore(prefix, link)
+
+ else:
+ # literatur item nur als bibliographische angabe vorhanden
+ link.setAttribute("alt", unicodify(res[0]['fullreference']))
+ link.setAttribute("title", "click to expand")
+ link.setAttribute("onclick", "return toggle(this);")
+ link.setAttribute("class", "x_offline")
+
+ # prefix inside link text
+ link.firstChild.data = '+ ' + link.firstChild.data
+ else:
+ # links zu den anderen datenbankobjekten
+ link.setAttribute("href",self.REQUEST['SERVER_URL']+"/references?id="+ref)
+ link.setAttribute("title", "click to view")
+ link.removeAttribute("ref")
+
+ # prefix preceding the link
+ prefix = dom.createTextNode(U"\u2013\u0020") # = ndash + space
+ dom.documentElement.insertBefore(prefix, link)
+
+ else:
+ # objekt nicht verfuegbar/freigegeben oder (web)link mit href statt ref
+
+ try:
+ link.removeAttribute("ref")
+ link.setAttribute("title", ref)
+ except:
+ pass
+
+
+ # prefix preceding the link
+ prefix = dom.createTextNode(U"\u2013\u0020") # = ndash + space
+ dom.documentElement.insertBefore(prefix, link)
+
+
+ newxml=dom.toxml('utf-8')
+
+ retStr=regexpTXT.search(newxml)
+ retStr = retStr.group(1)
+ #logging.debug("related2html out=%s"%repr(retStr))
+ return retStr.decode('utf-8') # we return unicode
+
+ return u""
+
+
+
+def xml2html(self,str,quote="yes"):
+ """link2html fuer VLP muss hier noch raus"""
+ if str:
+ if quote=="yes2":
+ str=re.sub("\&","&",str)
+ #dom=xml.dom.minidom.parseString(str)
+ #logging.debug("xml2html: str=%s"%(str))
+ #dom = NonvalidatingReader.parseString(str,"http://www.mpiwg-berlin.mpg.de/")
+ dom = ET.fromstring(str)
+ #links=dom.getElementsByTagName("link")
+ #links=Ft.Xml.XPath.Evaluate(".//link", contextNode=dom)
+ links = dom.findall(".//link")
+ for link in links:
+ #link.tagName="a"
+
+ #ref=link.getAttributeNS(EMPTY_NAMESPACE,"ref")
+ ref = link.get("ref", None)
+ #pn=link.getAttributeNS(EMPTY_NAMESPACE,"page")
+ pn = link.get("page", None)
+
+ # rename link tag to a
+ link.tag = "a"
+ # clear non-a-tag attributes
+ if ref is not None:
+ del link.attrib["ref"]
+ if pn is not None:
+ del link.attrib["page"]
+
+ #cns=link.childNodes[0:]
+
+ #newLink=dom.createElementNS(EMPTY_NAMESPACE,"a")
+ #for x in cns:
+ # newLink.appendChild(x)
+
+ #link.parentNode.replaceChild(newLink,link)
+
+ if self.checkRef(ref):
+ if pn:
+ link.set("href", self.REQUEST['SERVER_URL']+"/references?id="+ref+"&page="+pn)
+ #newLink.setAttributeNS(EMPTY_NAMESPACE,"href",self.REQUEST['SERVER_URL']+"/references?id="+ref+"&page="+pn)
+ else:
+ link.set("href", self.REQUEST['SERVER_URL']+"/references?id="+ref)
+ #newLink.setAttributeNS(EMPTY_NAMESPACE,"href",self.REQUEST['SERVER_URL']+"/references?id="+ref)
+
+ # remove outer page tag
+ if dom.tag == "page":
+ dom.tag = None
+
+ s = ET.tostring(dom, 'UTF-8')
+ # snip off XML declaration
+ if s.startswith('')
+ s = s[i+3:]
+
+ # convert to unicode object
+ str = unicodify(s)
+ return str
+
+ #str= dom.toxml('utf-8')
+ #buf = cStringIO.StringIO()
+ #PrettyPrint(dom, stream=buf)
+ #str = buf.getvalue()
+ #buf.close()
+ #str=PrettyPrint(dom.documentElement,encoding='UTF-8')
+ #print link.toxml('utf-8')
+ #print type(str)
+ #retStr=regexpPage.search(str)
+
+ #try: # hack warum fehtl manchmal page??
+ # return retStr.group(1).decode('utf-8')
+ #except:
+ # return str
+
+ return ""
+
+
+def xlink2html(self,xlink,parClass=None):
+ ret=""
+ attributes=xlink.attributes
+
+ if xlink.tagName.lower()=="image":
+ ret +="""
"""%xlink.getAttribute('href')
+ elif xlink.tagName.lower()=="link":
+ reference=urllib.unquote(xlink.getAttribute('href'))
+ label=getText(self,xlink.childNodes)
+
+ # check if href is already a correct url
+ if reference.split(":")[0] in ['http','file']:
+ if parClass=="Picture":
+ ret +=""""""%(reference)
+ else:
+
+ ret +="""%s"""%(reference,label)
+ else: # transform
+ #href=xml2html(self,reference)
+ #print "refer",reference
+ reference=re.sub("ref\=([^>]*)\>",'ref=\"\g<1>\">',reference)# einfuegen anfuehrungszeichen um ref attribut, falls fehlt.
+ ret +=reference
+
+ return ret
+
+def getText(self,nodelist,parClass=None):
+
+ rc = u''
+ for node in nodelist:
+
+ if node.nodeType == node.TEXT_NODE:
+
+ try:
+ try:
+ #rc += node.data.encode('utf-8','ignore')
+ rc += node.data
+
+ except:
+ #rc= node.data.encode('utf-8','ignore')
+ rc=node.data
+ except:
+ rc="ERROR"
+ #node.data.decode('utf-8','ignore')
+
+ node.data.encode('utf-8','ignore')
+ #print "RC",rc
+ elif node.tagName =="inline":
+
+ rc+=par2html(self,[node])
+
+ elif node.tagName =="pb":
+ rc+=""
+ elif node.attributes:
+
+ if 'type' in node.attributes.keys(): #is a xlink?
+
+ try:
+ rc +=xlink2html(self,node,parClass).encode('utf-8')
+
+ except:
+ rc +=xlink2html(self,node,parClass)
+
+ #print "RWT",rc
+ return rc
+
+
+#filename=argv[1]
+#fileString=file(filename).read()
+#print proj2hash(fileString)
diff -r 000000000000 -r 88009fd07d31 zpt/AddVLP_collectionForm.zpt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/zpt/AddVLP_collectionForm.zpt Wed Apr 17 14:54:21 2013 +0200
@@ -0,0 +1,39 @@
+
+
+ Add a new collection
+
+
+
diff -r 000000000000 -r 88009fd07d31 zpt/AddVLP_encyc.zpt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/zpt/AddVLP_encyc.zpt Wed Apr 17 14:54:21 2013 +0200
@@ -0,0 +1,16 @@
+
+
+ Add a new essay
+